Shahbuland Matiana's repositories
latent-space-explorer
Real-time latent exploration of diffusion models
valorant-skinfaker
Deepfakes weapon skins onto Valorant guns using CycleGAN
openbci-2d-motion
Uses EEG and Neural Network to classify thoughts and move cursor
Learning-Assistant
Using ChatGPT to simplify learning new concepts
AI-based-AudioVis
Audio visualizer using AI
CycleGAN-for-Videos
CycleGAN implementation specifically for video to video style transfer
destinygan
Automatically generating Destiny 2 loot using StyleGAN2 ADA and SWAGAN
adapter-experiments
Multimodal models everywhere
b-rabbit
A thread safe library that aims to provide a simple API for interfacing with RabbitMQ. Built on top of rabbitpy, the library make it very easy to use the RabbitMQ message broker with just few lines of code. It implements all messaging pattern used by message brokers
shahbuland_generative_models
Game generation
synthetic_mm
Synthetic multi modal data from captions with GPT-4
basic-gans
Just some GANs in pytorch
CARPforGO
Using CARP to contrastively learn representations from Board Configuration - Text Description pairs
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
DRLX-old
Reinforcement Learning + Diffusion Model library based on Karras et al. (2022) diffusion models for PyTorch
DuckTrack
Multimodal computer agent data collection program
embedding-reversal
Trying to invert embeddings to be used for generative modelling.
LatentCluster
Library to visualize neural network latent spaces easily, and then do stuff with those visualizations
mesh-transformer-jax
Model parallel transformers in JAX and Haiku
min-dalle-discordbot
A modified version of Min-DALLE that can be used as a discord server bot. Aim to be much less memory efficient than the original repo in order to be significantly faster, batch input, and use CLIP to rank generated output. Testing on an RTX 3090.
MultiModalPDFPipeline
Data pipeline to read PDFs with figures for multimodal model training
oslo_contrastive
OSLO: Open Source framework for Large-scale model Optimization
research-faster
Tool to research faster with a GPT-4 API key
trl
Train transformer language models with reinforcement learning.
vid-to-dataset
Script to convert videos into datasets that can be used to train a model